Simulation of drone controller using reinforcement learning AI with hyperparameter optimization
Drone is one of the latest drone technologies that grows with multiple applications; one of the critical applications is for fire-fighting drones such as water hose carrying for firefighting. One of the main challenges of the drone technologies is the non-linear dynamic movement caused by a variety...
Saved in:
Main Authors: | , , |
---|---|
Format: | Conference or Workshop Item |
Published: |
2020
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/92686/ http://dx.doi.org/10.1109/ICSET51301.2020.9265381 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.92686 |
---|---|
record_format |
eprints |
spelling |
my.utm.926862021-10-28T10:13:36Z http://eprints.utm.my/id/eprint/92686/ Simulation of drone controller using reinforcement learning AI with hyperparameter optimization Abu Bakar, Mohamad Hafiz Shamsudin, Abu Ubaidah Abdul Rahim, Ruzairi TK Electrical engineering. Electronics Nuclear engineering Drone is one of the latest drone technologies that grows with multiple applications; one of the critical applications is for fire-fighting drones such as water hose carrying for firefighting. One of the main challenges of the drone technologies is the non-linear dynamic movement caused by a variety of fire conditions. One solution is to use a nonlinear controller such as Reinforcement Learning. In this paper, Reinforcement Learning has been applied as their key control system to improve the conventional approach, which is the agent (drone) that will interact with the environment without need of the controller for the flying process. This paper is introduced an optimization method for the hyperparameter in order to achieve a better reward. In addition, we only concentrate on the learning rate (alpha) and potential reward factor discount (gamma) for optimization in this paper. From this optimization, the better performance and response from our result by using alpha = 0.1 & gamma = 0.8 with reward produced 6100 and it takes 49 seconds in the learning process. 2020 Conference or Workshop Item PeerReviewed Abu Bakar, Mohamad Hafiz and Shamsudin, Abu Ubaidah and Abdul Rahim, Ruzairi (2020) Simulation of drone controller using reinforcement learning AI with hyperparameter optimization. In: 10th IEEE International Conference on System Engineering and Technology, ICSET 2020, 9 November 2020, Shah Alam, Malaysia. http://dx.doi.org/10.1109/ICSET51301.2020.9265381 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Abu Bakar, Mohamad Hafiz Shamsudin, Abu Ubaidah Abdul Rahim, Ruzairi Simulation of drone controller using reinforcement learning AI with hyperparameter optimization |
description |
Drone is one of the latest drone technologies that grows with multiple applications; one of the critical applications is for fire-fighting drones such as water hose carrying for firefighting. One of the main challenges of the drone technologies is the non-linear dynamic movement caused by a variety of fire conditions. One solution is to use a nonlinear controller such as Reinforcement Learning. In this paper, Reinforcement Learning has been applied as their key control system to improve the conventional approach, which is the agent (drone) that will interact with the environment without need of the controller for the flying process. This paper is introduced an optimization method for the hyperparameter in order to achieve a better reward. In addition, we only concentrate on the learning rate (alpha) and potential reward factor discount (gamma) for optimization in this paper. From this optimization, the better performance and response from our result by using alpha = 0.1 & gamma = 0.8 with reward produced 6100 and it takes 49 seconds in the learning process. |
format |
Conference or Workshop Item |
author |
Abu Bakar, Mohamad Hafiz Shamsudin, Abu Ubaidah Abdul Rahim, Ruzairi |
author_facet |
Abu Bakar, Mohamad Hafiz Shamsudin, Abu Ubaidah Abdul Rahim, Ruzairi |
author_sort |
Abu Bakar, Mohamad Hafiz |
title |
Simulation of drone controller using reinforcement learning AI with hyperparameter optimization |
title_short |
Simulation of drone controller using reinforcement learning AI with hyperparameter optimization |
title_full |
Simulation of drone controller using reinforcement learning AI with hyperparameter optimization |
title_fullStr |
Simulation of drone controller using reinforcement learning AI with hyperparameter optimization |
title_full_unstemmed |
Simulation of drone controller using reinforcement learning AI with hyperparameter optimization |
title_sort |
simulation of drone controller using reinforcement learning ai with hyperparameter optimization |
publishDate |
2020 |
url |
http://eprints.utm.my/id/eprint/92686/ http://dx.doi.org/10.1109/ICSET51301.2020.9265381 |
_version_ |
1715189674850385920 |
score |
13.18916 |